Spatially aware cell cluster (SPACCL) graphs

An apparatus for predicting disease aggressiveness using a spatially aware cell cluster graph, comprising:

• a processor;
• a memory;
• an input/output interface;
• a set of logics;
• and
• an interface to connect the processor, the memory, the input/output interface and the set of logics, the set of logics comprising:
• an image acquisition logic that acquires an image of a region of tissue;
• a compartment classification logic that partitions the image into a stromal compartment and an epithelial compartment;
• a cluster node identification logic that identifies a cluster of nuclei as a cluster node;
• a sub-graph construction logic that constructs a stromal sub-graph GS and an epithelial sub-graph GE where the sub-graph construction logic constructs the stromal sub-graph GS by linking a first stromal cluster node and a second, different stromal cluster node, where the probability that the first stromal cluster node will be linked to the second stromal cluster node is based, at least in part, on a probabilistic decaying function of the distance between the first stromal cluster node and the second stromal cluster node, and where the sub-graph construction logic constructs the epithelial sub-graph GE by linking a first epithelial cluster node and a second, different epithelial cluster node, where the probability that the first epithelial cluster node will be linked to the second epithelial cluster node is based, at least in part, on a probabilistic decaying function of the distance between the first epithelial cluster node and the second epithelial cluster node;
• a feature extraction logic that extracts global features and local features from the stromal sub-graph GS and the epithelial sub-graph GE;
• and
• a disease aggressiveness prediction logic that produces electronic data that predicts the aggressiveness of a disease in the region of tissue, based, at least in part, on the global features and local features.

An apparatus comprising:

• a processor;
• a memory;
• an input/output interface;
• a set of logics;
• and
• an interface to connect the processor, the memory, the input/output interface and the set of logics, the set of logics comprising:
• a first logic that acquires an image of a region of interest;
• a second logic that partitions the image into at least a first compartment and a second compartment, where the second compartment is distinguishable from the first compartment;
• a third logic that identifies cluster nodes, where a cluster node identified in the first compartment is a first compartment cluster node, and a cluster node identified in the second compartment is a second compartment cluster node;
• a fourth logic that generates a first compartment sub-graph G1 and a second compartment sub-graph G2, where a sub-graph is generated by connecting a first cluster node in a compartment with a second, different cluster node in the same compartment, where the probability the first cluster node will be connected to the second cluster node is based on a probabilistic decaying function of the Euclidean distance between the first cluster node and the second cluster node, where the density of the sub-graph is controllable, and
• a fifth logic that extracts global metrics and local metrics from the sub-graphs G1 and G2 and controls an automated diagnostic system to classify the image, based, at least in part, on the global metrics and local metrics.